This repository hosts all my projects done in the domain of RNN

A machine learning software for extracting information from scholarly documents

Implemented different types of language models for modelling Indian names. There are clearly patterns in Indian names that models could learn, and we start modelling those using n-gram models, then move to neural n-gram and RNN models.

Used patterns in Indian names that models could learn, modelling those using n-gram models, then moved to neural n-gram and RNN models.

📳 From training of transformers to real-time development in cross-platform mobile apps!

Design of target-focused libraries by probing continuous fingerprint space with recurrent neural networks. The repository accompanies a research paper which is currently under review (08.04.24)

This project leverages machine learning and data science to analyse and predict English dialects in the UK and Ireland based on audio recordings, contributing to sociolinguistics and dialectology. The primary objective is to train a recurrent neural network (RNN) model to accurately predict dialects across various speakers and contexts.

Exercises on Machine Learning

Bolt is a deep learning library with high performance and heterogeneous flexibility.

RWKV is an RNN with transformer-level LLM performance. It can be directly trained like a GPT (parallelizable). So it's combining the best of RNN and transformer - great performance, fast inference, saves VRAM, fast training, "infinite" ctx_len, and free sentence embedding.

ChatRWKV is like ChatGPT but powered by RWKV (100% RNN) language model, and open source.

Perform the sentiment analysis task using Simple RNN

mage Captioning System using VggNet and LSTM Encoder-Decoder architecture

Official repository of the xLSTM.

Implied volatility is a key aspect when it comes to derivatives pricing. With the growing influence of machine learning in finance, I have investigated the use of LSTMs to forecast 1-day forward Implied Volatility.

This project is dedicated to implementing various machine learning algorithms from scratch to gain a deeper understanding of how they work.

Time series forecasting examples

A library built upon PyTorch for building embeddings on discrete event sequences using self-supervision

This repository contains a reading list of papers on Time Series Forecasting/Prediction (TSF) and Spatio-Temporal Forecasting/Prediction (STF). These papers are mainly categorized according to the type of model.

This repository introduces Artificial Intelligence with a focus on Long Short-Term Memory Recurrent Neural Networks (LSTM-RNN). Initially intended as supplementary lecture material, it helps readers understand LSTM-RNN and its evolution since the 1990s. Modern research on LSTM-RNN uses updated notations and more concise derivations.